Commit
·
09305b4
1
Parent(s):
d32a88f
End of training
Browse files- README.md +88 -0
- generation_config.json +6 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
model-index:
|
9 |
+
- name: t5-fine-tuned-with-25-yake-keywords
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# t5-fine-tuned-with-25-yake-keywords
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.7255
|
21 |
+
- Rouge1: 25.5557
|
22 |
+
- Rouge2: 11.1446
|
23 |
+
- Rougel: 20.7482
|
24 |
+
- Rougelsum: 24.0749
|
25 |
+
- Gen Len: 19.0
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 2
|
46 |
+
- eval_batch_size: 2
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 25
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
56 |
+
| 1.3097 | 1.0 | 604 | 1.3789 | 25.4996 | 11.1787 | 20.8197 | 23.9248 | 19.0 |
|
57 |
+
| 1.1951 | 2.0 | 1208 | 1.3779 | 25.3276 | 11.2651 | 20.6966 | 23.6966 | 19.0 |
|
58 |
+
| 1.1081 | 3.0 | 1812 | 1.3903 | 26.1128 | 11.8339 | 21.2543 | 24.5472 | 18.994 |
|
59 |
+
| 1.0272 | 4.0 | 2416 | 1.4042 | 26.0231 | 11.5574 | 21.152 | 24.3645 | 18.992 |
|
60 |
+
| 0.919 | 5.0 | 3020 | 1.4225 | 25.8646 | 11.6121 | 21.0205 | 24.3016 | 18.992 |
|
61 |
+
| 0.8643 | 6.0 | 3624 | 1.4410 | 25.9734 | 11.6221 | 21.0577 | 24.4231 | 18.99 |
|
62 |
+
| 0.8215 | 7.0 | 4228 | 1.4599 | 25.6546 | 11.2999 | 20.8896 | 24.2294 | 19.0 |
|
63 |
+
| 0.7931 | 8.0 | 4832 | 1.4926 | 25.0796 | 10.9369 | 20.3639 | 23.629 | 19.0 |
|
64 |
+
| 0.7664 | 9.0 | 5436 | 1.5090 | 25.4341 | 11.0028 | 20.6241 | 23.9038 | 19.0 |
|
65 |
+
| 0.7053 | 10.0 | 6040 | 1.5259 | 25.491 | 10.8959 | 20.5515 | 23.934 | 18.998 |
|
66 |
+
| 0.6725 | 11.0 | 6644 | 1.5481 | 25.3073 | 10.7089 | 20.4993 | 23.8286 | 19.0 |
|
67 |
+
| 0.6462 | 12.0 | 7248 | 1.5710 | 25.6276 | 11.0744 | 20.7313 | 24.1134 | 19.0 |
|
68 |
+
| 0.6275 | 13.0 | 7852 | 1.5884 | 25.8615 | 11.0844 | 20.9412 | 24.2996 | 19.0 |
|
69 |
+
| 0.5838 | 14.0 | 8456 | 1.6131 | 26.1201 | 11.4081 | 21.3173 | 24.6139 | 19.0 |
|
70 |
+
| 0.5682 | 15.0 | 9060 | 1.6259 | 25.7212 | 11.1367 | 20.8247 | 24.1398 | 19.0 |
|
71 |
+
| 0.5629 | 16.0 | 9664 | 1.6473 | 25.6506 | 11.2149 | 20.8629 | 24.1527 | 19.0 |
|
72 |
+
| 0.5446 | 17.0 | 10268 | 1.6645 | 25.4396 | 10.7189 | 20.4852 | 23.924 | 19.0 |
|
73 |
+
| 0.5108 | 18.0 | 10872 | 1.6716 | 25.7213 | 11.2197 | 20.858 | 24.3088 | 19.0 |
|
74 |
+
| 0.5358 | 19.0 | 11476 | 1.6882 | 25.7908 | 11.2416 | 20.9464 | 24.2852 | 19.0 |
|
75 |
+
| 0.4959 | 20.0 | 12080 | 1.7027 | 25.6556 | 11.2363 | 20.8495 | 24.1665 | 18.992 |
|
76 |
+
| 0.4942 | 21.0 | 12684 | 1.7131 | 25.6156 | 11.175 | 20.7688 | 24.1641 | 19.0 |
|
77 |
+
| 0.4833 | 22.0 | 13288 | 1.7178 | 25.7798 | 11.2421 | 20.896 | 24.2101 | 19.0 |
|
78 |
+
| 0.4702 | 23.0 | 13892 | 1.7227 | 25.7147 | 11.2161 | 20.9105 | 24.1549 | 19.0 |
|
79 |
+
| 0.4747 | 24.0 | 14496 | 1.7241 | 25.6314 | 11.1929 | 20.8068 | 24.1442 | 19.0 |
|
80 |
+
| 0.4691 | 25.0 | 15100 | 1.7255 | 25.5557 | 11.1446 | 20.7482 | 24.0749 | 19.0 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.34.0
|
86 |
+
- Pytorch 2.0.1+cu118
|
87 |
+
- Datasets 2.14.5
|
88 |
+
- Tokenizers 0.14.1
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.34.0"
|
6 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891702929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc649618996e6c47c5031291e9605be45e405ba2ecbaf3cb8604292083a83f3
|
3 |
size 891702929
|